mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-08-04 13:18:00 +02:00
Code Issues Releases Wiki Activity

Migrate DefinitionTest to use DirectLex for easier to read test-cases.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@109 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2006-07-24 01:22:51 +00:00
parent b251c4ed86
commit dfb3d48397
1 changed files with 59 additions and 183 deletions
Download Patch File Download Diff File Expand all files Collapse all files

242
tests/HTMLPurifier/DefinitionTest.php
View File

@@ -1,18 +1,30 @@
<?php <?php
require_once 'HTMLPurifier/Definition.php'; require_once 'HTMLPurifier/Definition.php';
require_once 'HTMLPurifier/Lexer.php'; require_once 'HTMLPurifier/Lexer/DirectLex.php';
class HTMLPurifier_DefinitionTest extends UnitTestCase class HTMLPurifier_DefinitionTest extends UnitTestCase
{ {
var $def, $lex; var $def, $lex, $gen;
function HTMLPurifier_DefinitionTest() { function HTMLPurifier_DefinitionTest() {
$this->UnitTestCase(); $this->UnitTestCase();
$this->def = new HTMLPurifier_Definition(); $this->def = new HTMLPurifier_Definition();
$this->def->loadData(); $this->def->loadData();
$this->lex = new HTMLPurifier_Lexer();
// we can't use the DOM lexer since it does too much stuff
// automatically, however, we should be able to use it
// interchangeably if we wanted to...
if (true) {
$this->lex = new HTMLPurifier_Lexer_DirectLex();
} else {
require_once 'HTMLPurifier/Lexer/DOMLex.php';
$this->lex = new HTMLPurifier_Lexer_DOMLex();
}
$this->gen = new HTMLPurifier_Generator();
} }
function test_removeForeignElements() { function test_removeForeignElements() {
@@ -20,44 +32,21 @@ class HTMLPurifier_DefinitionTest extends UnitTestCase
$inputs = array(); $inputs = array();
$expect = array(); $expect = array();
$inputs[0] = array(); $inputs[0] = '';
$expect[0] = $inputs[0]; $expect[0] = $inputs[0];
$inputs[1] = array( $inputs[1] = 'This is <b>bold text</b>.';
new HTMLPurifier_Token_Text('This is ')
,new HTMLPurifier_Token_Start('b', array())
,new HTMLPurifier_Token_Text('bold')
,new HTMLPurifier_Token_End('b')
,new HTMLPurifier_Token_Text(' text')
);
$expect[1] = $inputs[1]; $expect[1] = $inputs[1];
$inputs[2] = array( // [INVALID]
new HTMLPurifier_Token_Start('asdf') $inputs[2] = '<asdf>Bling</asdf><d href="bang">Bong</d><foobar />';
,new HTMLPurifier_Token_End('asdf') $expect[2] = htmlspecialchars($inputs[2]);
,new HTMLPurifier_Token_Start('d', array('href' => 'bang!'))
,new HTMLPurifier_Token_End('d')
,new HTMLPurifier_Token_Start('pooloka')
,new HTMLPurifier_Token_Start('poolasdf')
,new HTMLPurifier_Token_Start('ds', array('moogle' => '&'))
,new HTMLPurifier_Token_End('asdf')
,new HTMLPurifier_Token_End('asdf')
);
$expect[2] = array(
new HTMLPurifier_Token_Text('<asdf>')
,new HTMLPurifier_Token_Text('</asdf>')
,new HTMLPurifier_Token_Text('<d href="bang!">')
,new HTMLPurifier_Token_Text('</d>')
,new HTMLPurifier_Token_Text('<pooloka>')
,new HTMLPurifier_Token_Text('<poolasdf>')
,new HTMLPurifier_Token_Text('<ds moogle="&amp;">')
,new HTMLPurifier_Token_Text('</asdf>')
,new HTMLPurifier_Token_Text('</asdf>')
);
foreach ($inputs as $i => $input) { foreach ($inputs as $i => $input) {
$result = $this->def->removeForeignElements($input); $tokens = $this->lex->tokenizeHTML($input);
$this->assertEqual($expect[$i], $result); $result_tokens = $this->def->removeForeignElements($tokens);
$result = $this->gen->generateFromTokens($result_tokens);
$this->assertEqual($expect[$i], $result, "Test $i: %s");
paintIf($result, $result != $expect[$i]); paintIf($result, $result != $expect[$i]);
} }
@@ -68,122 +57,46 @@ class HTMLPurifier_DefinitionTest extends UnitTestCase
$inputs = array(); $inputs = array();
$expect = array(); $expect = array();
$inputs[0] = array(); $inputs[0] = '';
$expect[0] = $inputs[0]; $expect[0] = $inputs[0];
$inputs[1] = array( $inputs[1] = 'This is <b>bold text</b>.';
new HTMLPurifier_Token_Text('This is ')
,new HTMLPurifier_Token_Start('b')
,new HTMLPurifier_Token_Text('bold')
,new HTMLPurifier_Token_End('b')
,new HTMLPurifier_Token_Text(' text')
,new HTMLPurifier_Token_Empty('br')
);
$expect[1] = $inputs[1]; $expect[1] = $inputs[1];
$inputs[2] = array( $inputs[2] = '<b>Unclosed tag, gasp!';
new HTMLPurifier_Token_Start('b') $expect[2] = '<b>Unclosed tag, gasp!</b>';
,new HTMLPurifier_Token_Text('Unclosed tag, gasp!')
);
$expect[2] = array(
new HTMLPurifier_Token_Start('b')
,new HTMLPurifier_Token_Text('Unclosed tag, gasp!')
,new HTMLPurifier_Token_End('b')
);
$inputs[3] = array( $inputs[3] = '<b><i>Bold and italic?</b>';
new HTMLPurifier_Token_Start('b') $expect[3] = '<b><i>Bold and italic?</i></b>';
,new HTMLPurifier_Token_Start('i')
,new HTMLPurifier_Token_Text('The b is closed, but the i is not')
,new HTMLPurifier_Token_End('b')
);
$expect[3] = array(
new HTMLPurifier_Token_Start('b')
,new HTMLPurifier_Token_Start('i')
,new HTMLPurifier_Token_Text('The b is closed, but the i is not')
,new HTMLPurifier_Token_End('i')
,new HTMLPurifier_Token_End('b')
);
$inputs[4] = array( // CHANGE THIS BEHAVIOR!
new HTMLPurifier_Token_Text('Hey, recycle unused end tags!') $inputs[4] = 'Unused end tags... recycle!</b>';
,new HTMLPurifier_Token_End('b') $expect[4] = 'Unused end tags... recycle!&lt;/b&gt;';
);
$expect[4] = array(
new HTMLPurifier_Token_Text('Hey, recycle unused end tags!')
,new HTMLPurifier_Token_Text('</b>')
);
$inputs[5] = array(new HTMLPurifier_Token_Start('br', array('style' => 'clear:both;'))); $inputs[5] = '<br style="clear:both;">';
$expect[5] = array(new HTMLPurifier_Token_Empty('br', array('style' => 'clear:both;'))); $expect[5] = '<br style="clear:both;" />';
$inputs[6] = array(new HTMLPurifier_Token_Empty('div', array('style' => 'clear:both;'))); $inputs[6] = '<div style="clear:both;" />';
$expect[6] = array( $expect[6] = '<div style="clear:both;"></div>';
new HTMLPurifier_Token_Start('div', array('style' => 'clear:both;'))
,new HTMLPurifier_Token_End('div')
);
// test automatic paragraph closing // test automatic paragraph closing
$inputs[7] = array( $inputs[7] = '<p>Paragraph 1<p>Paragraph 2';
new HTMLPurifier_Token_Start('p') $expect[7] = '<p>Paragraph 1</p><p>Paragraph 2</p>';
,new HTMLPurifier_Token_Text('Paragraph 1')
,new HTMLPurifier_Token_Start('p')
,new HTMLPurifier_Token_Text('Paragraph 2')
);
$expect[7] = array(
new HTMLPurifier_Token_Start('p')
,new HTMLPurifier_Token_Text('Paragraph 1')
,new HTMLPurifier_Token_End('p')
,new HTMLPurifier_Token_Start('p')
,new HTMLPurifier_Token_Text('Paragraph 2')
,new HTMLPurifier_Token_End('p')
);
$inputs[8] = array( $inputs[8] = '<div><p>Paragraphs<p>In<p>A<p>Div</div>';
new HTMLPurifier_Token_Start('div') $expect[8] = '<div><p>Paragraphs</p><p>In</p><p>A</p><p>Div</p></div>';
,new HTMLPurifier_Token_Start('p')
,new HTMLPurifier_Token_Text('Paragraph 1 in a div')
,new HTMLPurifier_Token_End('div')
);
$expect[8] = array(
new HTMLPurifier_Token_Start('div')
,new HTMLPurifier_Token_Start('p')
,new HTMLPurifier_Token_Text('Paragraph 1 in a div')
,new HTMLPurifier_Token_End('p')
,new HTMLPurifier_Token_End('div')
);
// automatic list closing // automatic list closing
$inputs[9] = array( $inputs[9] = '<ol><li>Item 1<li>Item 2</ol>';
new HTMLPurifier_Token_Start('ol') $expect[9] = '<ol><li>Item 1</li><li>Item 2</li></ol>';
,new HTMLPurifier_Token_Start('li')
,new HTMLPurifier_Token_Text('Item 1')
,new HTMLPurifier_Token_Start('li')
,new HTMLPurifier_Token_Text('Item 2')
,new HTMLPurifier_Token_End('ol')
);
$expect[9] = array(
new HTMLPurifier_Token_Start('ol')
,new HTMLPurifier_Token_Start('li')
,new HTMLPurifier_Token_Text('Item 1')
,new HTMLPurifier_Token_End('li')
,new HTMLPurifier_Token_Start('li')
,new HTMLPurifier_Token_Text('Item 2')
,new HTMLPurifier_Token_End('li')
,new HTMLPurifier_Token_End('ol')
);
foreach ($inputs as $i => $input) { foreach ($inputs as $i => $input) {
$result = $this->def->makeWellFormed($input); $tokens = $this->lex->tokenizeHTML($input);
$this->assertEqual($expect[$i], $result); $result_tokens = $this->def->makeWellFormed($tokens);
$result = $this->gen->generateFromTokens($result_tokens);
$this->assertEqual($expect[$i], $result, "Test $i: %s");
paintIf($result, $result != $expect[$i]); paintIf($result, $result != $expect[$i]);
} }
@@ -196,68 +109,31 @@ class HTMLPurifier_DefinitionTest extends UnitTestCase
// next id = 4 // next id = 4
// legal inline nesting // legal inline nesting
$inputs[0] = array( $inputs[0] = '<b>Bold text</b>';
new HTMLPurifier_Token_Start('b'),
new HTMLPurifier_Token_Text('Bold text'),
new HTMLPurifier_Token_End('b'),
);
$expect[0] = $inputs[0]; $expect[0] = $inputs[0];
// legal inline and block // legal inline and block
// as the parent element is considered FLOW // as the parent element is considered FLOW
$inputs[1] = array( $inputs[1] = '<a href="about:blank">Blank</a><div>Block</div>';
new HTMLPurifier_Token_Start('a', array('href' => 'http://www.example.com/')),
new HTMLPurifier_Token_Text('Linky'),
new HTMLPurifier_Token_End('a'),
new HTMLPurifier_Token_Start('div'),
new HTMLPurifier_Token_Text('Block element'),
new HTMLPurifier_Token_End('div'),
);
$expect[1] = $inputs[1]; $expect[1] = $inputs[1];
// illegal block in inline, element -> text // illegal block in inline, element -> text
$inputs[2] = array( $inputs[2] = '<b><div>Illegal div.</div></b>';
new HTMLPurifier_Token_Start('b'), $expect[2] = '<b>&lt;div&gt;Illegal div.&lt;/div&gt;</b>';
new HTMLPurifier_Token_Start('div'),
new HTMLPurifier_Token_Text('Illegal Div'),
new HTMLPurifier_Token_End('div'),
new HTMLPurifier_Token_End('b'),
);
$expect[2] = array(
new HTMLPurifier_Token_Start('b'),
new HTMLPurifier_Token_Text('<div>'),
new HTMLPurifier_Token_Text('Illegal Div'),
new HTMLPurifier_Token_Text('</div>'),
new HTMLPurifier_Token_End('b'),
);
// test of empty set that's required, resulting in removal of node // test of empty set that's required, resulting in removal of node
$inputs[3] = array( $inputs[3] = '<ul></ul>';
new HTMLPurifier_Token_Start('ul'), $expect[3] = '';
new HTMLPurifier_Token_End('ul')
);
$expect[3] = array();
// test illegal text which gets removed // test illegal text which gets removed
$inputs[4] = array( $inputs[4] = '<ul>Illegal text<li>Legal item</li></ul>';
new HTMLPurifier_Token_Start('ul'), $expect[4] = '<ul><li>Legal item</li></ul>';
new HTMLPurifier_Token_Text('Illegal Text'),
new HTMLPurifier_Token_Start('li'),
new HTMLPurifier_Token_Text('Legal item'),
new HTMLPurifier_Token_End('li'),
new HTMLPurifier_Token_End('ul')
);
$expect[4] = array(
new HTMLPurifier_Token_Start('ul'),
new HTMLPurifier_Token_Start('li'),
new HTMLPurifier_Token_Text('Legal item'),
new HTMLPurifier_Token_End('li'),
new HTMLPurifier_Token_End('ul')
);
foreach ($inputs as $i => $input) { foreach ($inputs as $i => $input) {
$result = $this->def->fixNesting($input); $tokens = $this->lex->tokenizeHTML($input);
$this->assertEqual($expect[$i], $result); $result_tokens = $this->def->fixNesting($tokens);
$result = $this->gen->generateFromTokens($result_tokens);
$this->assertEqual($expect[$i], $result, "Test $i: %s");
paintIf($result, $result != $expect[$i]); paintIf($result, $result != $expect[$i]);
} }
} }